CN107886966A - Terminal and its method for optimization voice command, storage device - Google Patents
Terminal and its method for optimization voice command, storage device Download PDFInfo
- Publication number
- CN107886966A CN107886966A CN201711038813.XA CN201711038813A CN107886966A CN 107886966 A CN107886966 A CN 107886966A CN 201711038813 A CN201711038813 A CN 201711038813A CN 107886966 A CN107886966 A CN 107886966A
- Authority
- CN
- China
- Prior art keywords
- audio signal
- terminal
- audio
- frequency range
- header information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/038—Speech enhancement, e.g. noise reduction or echo cancellation using band spreading techniques
- G10L21/0388—Details of processing therefor
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/038—Speech enhancement, e.g. noise reduction or echo cancellation using band spreading techniques
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The present invention discloses a kind of terminal and its optimizes the method for voice command, storage device.Methods described includes:Receive or audio signal is gathered from current environment;Parsing audio signal simultaneously obtains the File header information of the audio signal;Audio processing algorithms are chosen according to the File header information;The bandwidth of audio signal is expanded by the audio processing algorithms of selection, and frequency range compensation is carried out to the frequency range of the audio signal after expansion.Based on this, the present invention can reduce hardware requirement while voice command discrimination is ensured, cost is low and versatile.
Description
Technical field
The present invention relates to electronic equipment and Audiotechnica field, and in particular to a kind of terminal and its side for optimizing voice command
Method, storage device.
Background technology
With the quick popularization of various electronic products, intellectuality, hommization of the user to terminal require more and more higher how
Make terminal more intelligent, specialized, diversified, and be more efficiently used in daily life, have become and currently grind
Study carefully one of direction.By taking AI (Artificial Intelligence, artificial intelligence) function based on speech recognition technology as an example,
In order to improve the discrimination of voice command, current many producers are only limited to use more preferable voice collector on end product
Part, but this very high hardware requirement, it can not only increase cost, and in order to realize that compatible needs enter to whole hardware system
Row redesigns, and versatility is poor.
The content of the invention
In consideration of it, the present invention provides a kind of terminal and its optimizes the method for voice command, storage device, language can ensured
Hardware requirement is reduced while sound command recognition rate, cost is low and versatile.
The method of the terminal optimized voice command of one embodiment of the invention, including:
Terminal receives or gathered from current environment audio signal;
Terminal parses audio signal and obtains the File header information of the audio signal;
Terminal chooses audio processing algorithms according to the File header information;
Terminal is expanded the bandwidth of audio signal by the audio processing algorithms of selection, and the audio after expansion is believed
Number frequency range carry out frequency range compensation.
The terminal with audio frequency process function of one embodiment of the invention, including processor, are connected with the processor
Digital signal processor DSP, wireless communicator and memory, and the sound pick-up being connected with the DSP, wherein,
Wireless communicator and sound pick-up are respectively used to receive or gather from current environment audio signal;
Processor is used to parse audio signal and obtains its File header information, and according to the File header information from storage
Audio processing algorithms are chosen in device;
DSP is used to expand the bandwidth of audio signal by the audio processing algorithms chosen, and to the sound after expansion
The frequency range of frequency signal carries out frequency range compensation.
The storage device of one embodiment of the invention, had program stored therein data, and described program data can be performed to realize
The method of above-mentioned terminal optimized voice command.
Beneficial effect:The present invention obtains the File header information of audio signal by parsing, and chooses suitable audio accordingly
Processing Algorithm, bandwidth expansion then is carried out to audio signal by the audio processing algorithms of selection and frequency range compensates, this pure calculation
The processing mode of method is relatively low to hardware requirement, therefore can reduce hardware requirement while voice command discrimination is ensured, into
This is low and versatile.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the method for the optimization voice command of first embodiment of the invention;
Fig. 2 is the conspectus of the sound pick-up collection audio signal of one embodiment of the invention;
Fig. 3 is the structural representation of the terminal of one embodiment of the invention;
Fig. 4 is the schematic flow sheet of the method for the optimization voice command of second embodiment of the invention.
Embodiment
The main object of the present invention is:The File header information of audio signal is obtained by parsing, and according to File header information
Suitable audio processing algorithms are chosen, then the bandwidth of audio signal is expanded by the audio processing algorithms of selection, with
And frequency range compensation is carried out to the frequency range of the audio signal after expansion, the processing mode of this pure algorithm is relatively low to hardware requirement, because
This can reduce hardware requirement while voice command discrimination is ensured, cost is low and versatile.
The terminal that the present invention is applicable can be electronic consumer devices, smart mobile phone, portable communication appts, PDA
The mobile terminal such as (Personal Digital Assistant, personal digital assistant or tablet personal computer), notebook computer, also may be used
To be the wearable device for being worn on limbs or being embedded in clothing, jewellery, accessory, it can also be that other have audio frequency process
The electronic equipment of function.
Below in conjunction with the accompanying drawing in the embodiment of the present invention, to the skill of each exemplary embodiment provided by the present invention
Art scheme is clearly and completely described.In the case where not conflicting, following each embodiments and its technical characteristic can be mutual
Combination.
Fig. 1 is the schematic flow sheet of the method for the optimization voice command of first embodiment of the invention.Referring to Fig. 1, this reality
Step S11~S14 can be included by applying the optimization voice command method of example.
S11:Terminal receives or gathered from current environment audio signal.
In the present embodiment, terminal can obtain audio signal by two ways:
First, terminal is downloaded from network and high in the clouds, or received from the other equipment to be established a connection with terminal.Example
Such as, terminal can access network and high in the clouds by modules such as the bluetooth of itself, Wi-Fi and networks, or be built with other equipment
Vertical annexation, and thus obtain audio signal.Now, the audio signal that terminal obtains is digital audio and video signals.
Second, terminal gathers audio signal by sound pick-ups such as microphones from current environment.In the present embodiment, this is picked up
Sound device can be simulation microphone, and the audio signal that sound pick-up collects is simulated audio signal, it is exported and analog audio
Frequency signal, for the ease of subsequently carrying out various digital processings to audio signal, terminal can be by sound pick-up and analog-digital converter
(Analog-to-Digital Converter, ADC) is connected, after the analog-to-digital conversion that simulated audio signal passes through analog-digital converter
It is changed into digital audio and video signals, and continues to be transferred to the subsequent conditioning circuit of terminal to carry out various digital processings.Certainly, the present embodiment
Sound pick-up can also be digital microphone, and the great advantage of digital microphone is strong antijamming capability, without as traditional microphones
Built-in like that high-frequency filter capacitor and filter circuit, also, due to digital microphone output be digital audio and video signals, because
This terminal can be connected with subsequent conditioning circuit directly by sound pick-up and carry out various digital processings.
It should be understood that the sound pick-up of the present embodiment is including but not limited to above-mentioned.For example, terminal can also be by vibrating motor simultaneously
Audio signal is gathered from current environment based on counter electromotive force principle, specifically:Based on Faraday's electromagnetic induction law, vibration electricity
AC (Alternating Current, alternating current) signal in machine produces the magnetic field of change on coil, produces electromagnetic induction electricity
Kinetic potential, at the same time, people speak caused by audio signal air pressure is changed, shaken by vibrating surrounding air to cause
The diaphragm vibration of dynamic motor, based on lenz' law, impinged upon when being vibrated caused by vibration caused by audio signal and electromagnetic induction
During same diaphragm, external force direction that diaphragm is subject on the contrary, vibrating motor can produce the electromotive force opposite with electromagnetic induction electromotive force,
That is counter electromotive force.Digital audio and video signals are can obtain by monitoring electric current caused by counter electromotive force, and by electroacoustic conversion.Compare
Compared with microphone, the diaphragm effective coverage (region for being adapted to sound to hit) of vibrating motor is bigger, can capture wider frequency range
Audio signal, advantageously in improve voice command discrimination.
In the present embodiment, the target sound source in current environment (such as mankind) can play 20Hz-20kHz just
String ripple signal, the sound pick-up of terminal can move along netted route and gather the audio analog signals in current environment.Specifically,
As shown in Fig. 2 speaking on direction in target sound source, sound pick-up can move along progressively or column by column, and gather audio signal.
S12:Terminal parses audio signal and obtains the File header information of the audio signal.
Resolved audio signal is digital audio and video signals, and the File header information of acquisition includes but is not limited to sample rate, ratio
At least one of special rate, bandwidth and data byte digit.
S13:Terminal chooses audio processing algorithms according to File header information.
What terminal was chosen to obtain is the audio processing algorithms most matched with the various data that File header information is included, the sound
Frequency Processing Algorithm processing audio signal efficiency and quality it is optimal, such as bandwidth expansion and frequency range compensation efficiency and quality most
It is good.Based on this, the present embodiment is not intended to limit the type of audio processing algorithms and its carries out bandwidth expansion and the principle of frequency range compensation
And process.
S14:Terminal is expanded the bandwidth of audio signal by the audio processing algorithms of selection, and to the sound after expansion
The frequency range of frequency signal carries out frequency range compensation.
In a kind of application scenarios, audio processing algorithms can be by audio signal (voice) in 20Hz-20kHz frequency range
Frequency modification is carried out to change its audio curve.For example, audio processing algorithms first by the audio signal collected from 8kHz bands
Pair width is extended for 16kHz, makes up the part voice of loss, then carries out frequency range compensation to the frequency range of wherein low sampling rate, i.e.,
Audio signal after expansion is repaired so that the part voice made up more conforms to actual voice feature.
From the foregoing, the present embodiment is essentially by pure algorithm process audio signal, to the degree of dependence of hardware compared with
Low, voice command discrimination can ensured using the high voice collecting device of performance, the present embodiment by being compared to prior art
While reduce hardware requirement, cost is low, and without in order to realize it is compatible whole hardware system is redesigned, it is general
Property is strong.
On aforementioned base, terminal can be based on speech recognition (Automatic Speech Recognition, ASR) technology
Audio signal after algorithm process is converted into character instruction.Speech recognition technology is to convert voice signals into the words such as word
The technology of symbol, it depends on acoustic model, pronunciation word library and language form storehouse.Wherein, acoustic model is that have by training
The statistical model of element, the phoneme of its audio signal after being handled by recognizer obtain corresponding aligned phoneme sequence, Ran Houben
These phonemes are compared in pronunciation word library for invention, list candidate word and the possible pronunciation of these candidate words, based on
The aligned phoneme sequence matched somebody with somebody, most possible word is selected from these candidate words, be ginseng in conjunction with the grammer included by language model
According to drawing character instruction.
Certainly, the audio signal after algorithm process can also be uploaded to high in the clouds by terminal.
If it should be appreciated that above-mentioned function is realized in the form of software function and sells or use as stand-alone product
When, it is storable in an electronic device-readable and takes in storage medium, i.e. the present invention also provides a kind of depositing for data that have program stored therein
Storage device, described program data can be performed to realize the method for above-described embodiment, and the storage device can be such as USB flash disk, light
Disk, server etc..That is, above-described embodiment can be embodied in the form of software product, it includes some instructions use
To cause a station terminal to perform all or part of step of methods described.
In practical application scene, in view of the structure design of terminal is different, the structure devices of above-mentioned each step are performed
Differ.It is described below by taking the terminal 30 shown in Fig. 3 as an example.
Referring to Fig. 3, terminal 30 can include sound pick-up 31, audio decoder 32, DSP (Digital Signal
Processing, digital signal processor) 33, processor 34, memory 35 and wireless communicator 36, sound pick-up 31 and DSP
33 connections, DSP 33, memory 35 and wireless communicator 36 are connected with processor 34.Certainly, terminal 30 can also include electricity
Source control unit, the PMU and sound pick-up 31, audio decoder 32, DSP 33, processor 34 and radio communication
Device 36 connects, and for managing the power supply to each structural detail.
Processor 34 is used for the operating system for running terminal 30, and carries out task management to each structural detail, such as ties
The upper electricity of constitutive element part, after hardware initialization and in due course between start and play thread, decoding thread, create track, audio mixing
Deng operation.
Audio decoder 32 is used to provide at least one interface to support the access of input-output apparatus, and ensures to be connect
The normal work of the input-output apparatus entered, such as the interface of audio decoder 32 include loudspeaker power amplifier, digital-to-analog Mike
The interface of wind.Sound pick-up 31 is used as an input-output apparatus, for gathering audio signal from current environment.The sound pick-up
31 can be simulation microphone, and now audio signal is simulated audio signal, and audio decoder 32 is built-in with analog-digital converter
(Analog-to-Digital Converter, ADC), it is changed into after the analog-to-digital conversion that simulated audio signal passes through analog-digital converter
Digital audio and video signals, and continue to be transferred to DSP 33.Certainly, the sound pick-up 31 can also be digital microphone, and it is directly exported
Digital audio and video signals.
Digital audio and video signals can be sent to processor 34 by DSP 33 after analog-to-digital conversion is carried out to simulated audio signal, be handled
Device 34 is used to parse the digital audio and video signals and obtains its File header information, and according to the File header information from memory
Suitable audio processing algorithms are chosen in 35.Wherein, File header information include but is not limited to sample rate, bit rate, bandwidth and
At least one of data byte digit.The message of the audio processing algorithms of selection is passed through I2C (Inter- by processor 34
Integrated Circuit, twin wire universal serial bus) burning enters in DSP 33.
DSP 33 is expanded the bandwidth of audio signal by audio processing algorithms, and to the audio signal after expansion
Frequency range carries out frequency range compensation.The DSP 33 has memory buffer pond, for avoiding in audio processing algorithms processing audio signal
During there is the problem of resource is seized.The main function of this audio processing algorithms is the audio signal that will collect from 8kHz bands
Pair width is extended for 16kHz, makes up the part voice of loss, then carries out frequency range compensation to the frequency range of wherein low sampling rate, i.e.,
Audio signal after expansion is repaired so that the part voice made up more conforms to actual voice feature.In the present embodiment
In, in view of the audio signal after the DSP 33 processing is PCM (pulse code modulation, Pulse Code Modulation) form
Data, therefore processor 34 to the audio signal after algorithm process without carrying out coded treatment.
Memory 35 is used to preserve various types of audio processing algorithms and audio signal, and is used as caching by each step
The data that rapid processing is completed are deposited temporarily, in order to the calling of processor 34.For example, processor 34 can call processing to complete
Audio signal afterwards, and character instruction is converted into, high in the clouds, or processor 34 are then uploaded to by wireless communicator 36
Calling processing after the completion of audio signal and it is directly uploaded to high in the clouds.
Wireless communicator 36 is used to send and receive from the local data for being sent to high in the clouds, or receives due to local transmission
Order and the voice data that is fed back from high in the clouds.For example, the wireless communicator 36 can with the bluetooth of itself, Wi-Fi and
The modules such as network access network and high in the clouds is downloaded, or are established a connection with other equipment, and thus obtain audio signal, this
When the audio signal that obtains be digital audio and video signals.In order to ensure the complete and efficient processing locality of data, channel radio
Believe device 36 first by the data buffer storage of reception into memory 35.
Referring to Fig. 4, the concrete application example of method one of optimization voice command is performed for terminal 30.The embodiment is realizing
The whole process of present invention, therefore not to repeat here.
Embodiments of the invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, for example, between each embodiment technical characteristic it is mutual
With reference to, or other related technical areas are directly or indirectly used in, it is included within the scope of the present invention.
Claims (10)
- A kind of 1. method of terminal optimized voice command, it is characterised in that methods described includes:Terminal receives or gathered from current environment audio signal;The terminal parses the audio signal and obtains the File header information of the audio signal;The terminal chooses audio processing algorithms according to the File header information;The terminal is expanded the bandwidth of the audio signal by the audio processing algorithms of selection, and to the sound after expansion The frequency range of frequency signal carries out frequency range compensation.
- 2. according to the method for claim 1, it is characterised in that the File header information includes sample rate, bit rate, band At least one of wide and data byte digit.
- 3. according to the method for claim 1, it is characterised in that the frequency range of the audio signal after described pair of expansion carries out frequency range After compensation, methods described also includes:Audio signal after frequency range compensates is uploaded to high in the clouds by the terminal, or will be through overfrequency based on speech recognition technology Audio signal after section compensation is converted to character instruction.
- 4. according to the method for claim 1, it is characterised in that the terminal gathers audio signal by sound pick-up, described Sound pick-up includes one in simulation microphone and digital microphone, and the simulation microphone gathers analog audio from current environment Frequency signal, simulated audio signal described in the terminal-pair carry out analog-to-digital conversion and obtain the audio signal.
- 5. according to the method for claim 1, it is characterised in that the terminal is by the audio processing algorithms of selection by described in The bandwidth of audio signal is extended for 16kHz from 8kHz.
- 6. a kind of terminal with audio frequency process function, it is characterised in that the terminal includes processor, connects with the processor Digital signal processor DSP, wireless communicator and the memory connect, and the sound pick-up being connected with the DSP, wherein,The wireless communicator and the sound pick-up are respectively used to receive or gather from current environment audio signal;The processor is used to parse the audio signal and obtains its File header information, and according to the File header information from Audio processing algorithms are chosen in the memory;The DSP be used for by selection audio processing algorithms the bandwidth of the audio signal is expanded, and to expansion after Audio signal frequency range carry out frequency range compensation.
- 7. terminal according to claim 6, it is characterised in that the File header information includes sample rate, bit rate, band At least one of wide and data byte digit.
- 8. terminal according to claim 6, it is characterised in that the processor is additionally operable to the sound after frequency range compensates Frequency signal is uploaded to high in the clouds, or the audio signal after frequency range compensates is converted into character based on speech recognition technology and referred to Order.
- 9. terminal according to claim 6, it is characterised in that the sound pick-up includes simulation microphone and digital microphone In one, the simulation microphone is used to gather simulated audio signal from current environment, and the terminal also turns including modulus Parallel operation, the analog-digital converter are used to carry out analog-to-digital conversion to the simulated audio signal and obtain the audio signal.
- 10. a kind of storage device, it is characterised in that the storage device is had program stored therein data, and described program data can be by Perform to realize the method described in claim any one of 1-5.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711038813.XA CN107886966A (en) | 2017-10-30 | 2017-10-30 | Terminal and its method for optimization voice command, storage device |
PCT/CN2018/112804 WO2019085914A1 (en) | 2017-10-30 | 2018-10-30 | Terminal, voice command optimization method therefor and storage apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711038813.XA CN107886966A (en) | 2017-10-30 | 2017-10-30 | Terminal and its method for optimization voice command, storage device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107886966A true CN107886966A (en) | 2018-04-06 |
Family
ID=61782987
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711038813.XA Pending CN107886966A (en) | 2017-10-30 | 2017-10-30 | Terminal and its method for optimization voice command, storage device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107886966A (en) |
WO (1) | WO2019085914A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019085914A1 (en) * | 2017-10-30 | 2019-05-09 | 捷开通讯(深圳)有限公司 | Terminal, voice command optimization method therefor and storage apparatus |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1736127A (en) * | 2003-01-09 | 2006-02-15 | 诺基亚公司 | Audio signal processing |
CN1849647A (en) * | 2003-09-30 | 2006-10-18 | 松下电器产业株式会社 | Sampling rate conversion apparatus, coding apparatus, decoding apparatus and methods thereof |
US20080300866A1 (en) * | 2006-05-31 | 2008-12-04 | Motorola, Inc. | Method and system for creation and use of a wideband vocoder database for bandwidth extension of voice |
CN101751925A (en) * | 2008-12-10 | 2010-06-23 | 华为技术有限公司 | Tone decoding method and device |
CN101763859A (en) * | 2009-12-16 | 2010-06-30 | 深圳华为通信技术有限公司 | Method and device for processing audio-frequency data and multi-point control unit |
CN102610231A (en) * | 2011-01-24 | 2012-07-25 | 华为技术有限公司 | Method and device for expanding bandwidth |
US20130151255A1 (en) * | 2011-12-07 | 2013-06-13 | Gwangju Institute Of Science And Technology | Method and device for extending bandwidth of speech signal |
CN103262409A (en) * | 2010-09-10 | 2013-08-21 | Dts(英属维尔京群岛)有限公司 | Dynamic compensation of audio signals for improved perceived spectral imbalances |
CN103413557A (en) * | 2013-07-08 | 2013-11-27 | 深圳Tcl新技术有限公司 | Voice signal bandwidth expansion method and device thereof |
CN103915104A (en) * | 2012-12-31 | 2014-07-09 | 华为技术有限公司 | Signal bandwidth expansion method and user equipment |
CN105118514A (en) * | 2015-08-17 | 2015-12-02 | 惠州Tcl移动通信有限公司 | A method and earphone for playing lossless quality sound |
CN105188075A (en) * | 2014-06-17 | 2015-12-23 | 中国移动通信集团公司 | Voice quality optimization method and device and terminal |
CN105324814A (en) * | 2013-06-25 | 2016-02-10 | 奥林奇公司 | Improved frequency band extension in an audio signal decoder |
JP2016038409A (en) * | 2014-08-05 | 2016-03-22 | 沖電気工業株式会社 | Voice band extension device and program, and voice feature amount extraction device and program |
CN105637583A (en) * | 2013-09-10 | 2016-06-01 | 华为技术有限公司 | Adaptive bandwidth extension and apparatus for the same |
CN107087069A (en) * | 2017-04-19 | 2017-08-22 | 维沃移动通信有限公司 | A kind of audio communication method and mobile terminal |
CN107221334A (en) * | 2016-11-01 | 2017-09-29 | 武汉大学深圳研究院 | The method and expanding unit of a kind of audio bandwidth expansion |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070109977A1 (en) * | 2005-11-14 | 2007-05-17 | Udar Mittal | Method and apparatus for improving listener differentiation of talkers during a conference call |
CO6440537A2 (en) * | 2009-04-09 | 2012-05-15 | Fraunhofer Ges Forschung | APPARATUS AND METHOD TO GENERATE A SYNTHESIS AUDIO SIGNAL AND TO CODIFY AN AUDIO SIGNAL |
CN103971694B (en) * | 2013-01-29 | 2016-12-28 | 华为技术有限公司 | The Forecasting Methodology of bandwidth expansion band signal, decoding device |
US9319510B2 (en) * | 2013-02-15 | 2016-04-19 | Qualcomm Incorporated | Personalized bandwidth extension |
CN105847497A (en) * | 2016-03-28 | 2016-08-10 | 乐视控股(北京)有限公司 | Voice signal processing method and voice signal processing device |
CN106960672B (en) * | 2017-03-30 | 2020-08-21 | 国家计算机网络与信息安全管理中心 | Bandwidth extension method and device for stereo audio |
CN107886966A (en) * | 2017-10-30 | 2018-04-06 | 捷开通讯(深圳)有限公司 | Terminal and its method for optimization voice command, storage device |
-
2017
- 2017-10-30 CN CN201711038813.XA patent/CN107886966A/en active Pending
-
2018
- 2018-10-30 WO PCT/CN2018/112804 patent/WO2019085914A1/en active Application Filing
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1736127A (en) * | 2003-01-09 | 2006-02-15 | 诺基亚公司 | Audio signal processing |
CN1849647A (en) * | 2003-09-30 | 2006-10-18 | 松下电器产业株式会社 | Sampling rate conversion apparatus, coding apparatus, decoding apparatus and methods thereof |
US20080300866A1 (en) * | 2006-05-31 | 2008-12-04 | Motorola, Inc. | Method and system for creation and use of a wideband vocoder database for bandwidth extension of voice |
CN101751925A (en) * | 2008-12-10 | 2010-06-23 | 华为技术有限公司 | Tone decoding method and device |
CN101763859A (en) * | 2009-12-16 | 2010-06-30 | 深圳华为通信技术有限公司 | Method and device for processing audio-frequency data and multi-point control unit |
CN103262409A (en) * | 2010-09-10 | 2013-08-21 | Dts(英属维尔京群岛)有限公司 | Dynamic compensation of audio signals for improved perceived spectral imbalances |
EP2660812A1 (en) * | 2011-01-24 | 2013-11-06 | Huawei Technologies Co., Ltd. | Bandwidth expansion method and apparatus |
CN102610231A (en) * | 2011-01-24 | 2012-07-25 | 华为技术有限公司 | Method and device for expanding bandwidth |
US20130151255A1 (en) * | 2011-12-07 | 2013-06-13 | Gwangju Institute Of Science And Technology | Method and device for extending bandwidth of speech signal |
CN103915104A (en) * | 2012-12-31 | 2014-07-09 | 华为技术有限公司 | Signal bandwidth expansion method and user equipment |
CN105324814A (en) * | 2013-06-25 | 2016-02-10 | 奥林奇公司 | Improved frequency band extension in an audio signal decoder |
CN103413557A (en) * | 2013-07-08 | 2013-11-27 | 深圳Tcl新技术有限公司 | Voice signal bandwidth expansion method and device thereof |
CN105637583A (en) * | 2013-09-10 | 2016-06-01 | 华为技术有限公司 | Adaptive bandwidth extension and apparatus for the same |
CN105188075A (en) * | 2014-06-17 | 2015-12-23 | 中国移动通信集团公司 | Voice quality optimization method and device and terminal |
JP2016038409A (en) * | 2014-08-05 | 2016-03-22 | 沖電気工業株式会社 | Voice band extension device and program, and voice feature amount extraction device and program |
CN105118514A (en) * | 2015-08-17 | 2015-12-02 | 惠州Tcl移动通信有限公司 | A method and earphone for playing lossless quality sound |
CN107221334A (en) * | 2016-11-01 | 2017-09-29 | 武汉大学深圳研究院 | The method and expanding unit of a kind of audio bandwidth expansion |
CN107087069A (en) * | 2017-04-19 | 2017-08-22 | 维沃移动通信有限公司 | A kind of audio communication method and mobile terminal |
Non-Patent Citations (4)
Title |
---|
中国铁路总公司: "《高速铁路通信技术——业务网》", 30 April 2016, 中国铁道出版社 * |
何勇军 等: "语音识别中带宽失配的补偿研究", 《计算机学报》 * |
张勇 等: "窄带语音带宽扩展算法研究", 《声学学报》 * |
李念芦 等: "《影视技术基础》", 28 February 2016, 北京联合出版公司 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019085914A1 (en) * | 2017-10-30 | 2019-05-09 | 捷开通讯(深圳)有限公司 | Terminal, voice command optimization method therefor and storage apparatus |
Also Published As
Publication number | Publication date |
---|---|
WO2019085914A1 (en) | 2019-05-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9542938B2 (en) | Scene recognition method, device and mobile terminal based on ambient sound | |
US20190355354A1 (en) | Method, apparatus and system for speech interaction | |
CN108550367A (en) | A kind of portable intelligent interactive voice control device, method and system | |
CN108549206A (en) | A kind of band has the smartwatch of voice interactive function earphone | |
CN109087660A (en) | Method, apparatus, equipment and computer readable storage medium for echo cancellor | |
CN104883437A (en) | Method and system for adjusting the volume of warning tone through environment-based voice analysis | |
CN104092801A (en) | Intelligent terminal call noise reduction method and intelligent terminal | |
CN108922528A (en) | Method and apparatus for handling voice | |
CN111276135B (en) | Network voice recognition method, network service interaction method and intelligent earphone | |
CN109712623A (en) | Sound control method, device and computer readable storage medium | |
CN109215666A (en) | Intelligent Supports Made, the transmission method of audio signal, human-computer interaction method and terminal | |
CN109545216A (en) | A kind of audio recognition method and speech recognition system | |
CN107680594A (en) | A kind of distributed intelligence voice collecting identifying system and its collection and recognition method | |
CN207010925U (en) | A kind of Headphone device for carrying voice and waking up identification | |
CN111276150A (en) | Intelligent voice-to-character and simultaneous interpretation system based on microphone array | |
CN107886966A (en) | Terminal and its method for optimization voice command, storage device | |
CN102322928B (en) | Electronic scale, mobile equipment, body weight measuring system and wireless transmission method | |
CN107357174A (en) | A kind of distributed intelligence audio amplifier speech control system | |
CN104618845A (en) | Method for monitoring surrounding sound and portable mobile device | |
CN207181990U (en) | A kind of distributed intelligence audio amplifier speech control system | |
CN110971968A (en) | Intelligent set top box system | |
CN104348436B (en) | A kind of parameter regulation means and electronic equipment | |
CN104933642A (en) | Tour guide machine service system based on single-chip microcomputer | |
CN108235185A (en) | Source of sound input client device, remote controler and the system for playing music | |
CN208691520U (en) | WIFI speaker |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180406 |